EP3541288A1 - Method for predicting a specific respiratory pathogen - Google Patents

Method for predicting a specific respiratory pathogen

Info

Publication number
EP3541288A1
EP3541288A1 EP17844655.5A EP17844655A EP3541288A1 EP 3541288 A1 EP3541288 A1 EP 3541288A1 EP 17844655 A EP17844655 A EP 17844655A EP 3541288 A1 EP3541288 A1 EP 3541288A1
Authority
EP
European Patent Office
Prior art keywords
rdi
respiratory
group
pathogen
sounds
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP17844655.5A
Other languages
German (de)
French (fr)
Other versions
EP3541288B1 (en
Inventor
Marika Christine GENZOW
Charles Oliver GOMEZ-DURAN
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Boehringer Ingelheim Vetmedica GmbH
Original Assignee
Boehringer Ingelheim Vetmedica GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Boehringer Ingelheim Vetmedica GmbH filed Critical Boehringer Ingelheim Vetmedica GmbH
Publication of EP3541288A1 publication Critical patent/EP3541288A1/en
Application granted granted Critical
Publication of EP3541288B1 publication Critical patent/EP3541288B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00—Other apparatus for animal husbandry
    • A01K29/005—Monitoring or measuring activity
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00—Instruments for auscultation
    • A61B7/003—Detecting lung or respiration noise
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters

Definitions

  • the invention relates to a method carried out by a processor for predicting a specific respiratory pathogen in a group of farm animals comprising recording the sounds; converting the analog recording into digital data; filtering off background noises from sounds caused by respiratory distress; comparing the resulting the respiratory distress index (RDI) pattern with a stored table containing data of different RDI patterns generated by several different respiratory pathogens; and reporting the respiratory pathogen, which corresponds to the matching RDI patterns.
  • RDI respiratory distress index
  • the invention relates to a non-transitory processor readable medium having stored thereon processor executable instructions configured to cause a processor to perform the method according to the invention, a computing device to carry out the method according to the invention, and a kit of parts for carrying out the inventive method comprising such a computing device and at least one microphone.
  • Livestock farming may be regarded as a process control technology, in which context the Precision Livestock Farming (PLF) is often used (Berckmans, D. 2006, in Livestock Production and Society, R. Geers, and F. Madec, eds. Wageningen Academic Publishers. 51-54).
  • PLF Precision Livestock Farming
  • sensors e.g., cameras (CCTV, infra-red, 3D, thermal...), accelerometers, flow meters, etc.
  • a particularly interesting type of PLF techniques uses microphones to capture sound. Sound contains a lot of useful information about the animal and its environment (communication, health, welfare). Recently, a number of examples of sound-based PLF -techno logy have emerged in different species.
  • Moura et al. showed how thermal (dis-) comfort can be monitored in broilers based on sound analysis (Moura, D.J. de, Naiis, I. de A., Alves, E.C. de S., Carvalho, T.M.R. de, do Vale, M.M., and Lima, K.A.O. de 2008, Sci. Agric. 65, 438- 443), while Aydin et al. demonstrated the monitoring of broiler feed intake by pecking sounds (Aydin, A., Bahr, C, Viazzi, S., Exadaktylos, V., Buyse, J., and Berckmans, D. 2014. Comput. Electron. Agric.
  • Hillman et al. used acoustic monitoring of pigs for the detection of thermal (dis-) comfort (Hillmann, E., Mayer, C, Schon, P.-C, Puppe, B., and Schrader, L. 2004, Appl. Anim. Behav. Sci. 89, 195-206).
  • Van Hirtum et al. first developed algorithms to discriminate pathological from non-pathological pig coughs (Van Hirtum, A. 2002. The acoustics of coughing. PhD Thesis. KU Leuven. Leuven,
  • Ferrari et al. did a characterisation of pig cough sounds using time and frequency-derived parameters (Ferrari et al., 2008),
  • the European patent application EP 2783 629 Al discloses a method and/or system for monitoring the sounds of a group of farm animals with a microphone connected with a computing device, in which the computing device records the sounds made by the animals, performs filtering operations to filter off background noises, counting the number of sounds caused by respiratory distress over a certain period of time and alerts an operator, if the registered number of sounds caused by respiratory distress exceeds a given value.
  • the International patent application WO 2008/152433 teaches a method and/or system for combining the respiratory status (e.g. amount and type of cough) with the localization of organisms having the respiratory status in real time. Furthermore, it suggests that the type of cough may be recognized utilizing Auto Regression analysis. However, the hitherto described methods are not capable to predict the pathogen, which causes the respiratory distress of the animals monitored. Accordingly, there is a high demand for a
  • the problem underlying the present invention was to provide a method to measure sounds caused by respiratory stress in farm animals, which allows predicting the pathogen causing the respiratory stress.
  • each respiratory pathogen creates a distinctive pattern of the respiratory distress index (RDI) being the number of sounds caused by respiratory distress per single farm animal within a pre-defined period.
  • RDI respiratory distress index
  • the problem underlying the present invention has been solved by a method wherein the pattern of the RDI is measured, monitored and stored period of time and compared with a table in which different RDI patterns are stored.
  • the invention relates to a method for predicting a specific respiratory pathogen in a group of farm animals, comprising the following steps:
  • RDI respiratory distress index
  • the invention further relates to a non-transitory processor readable medium having stored thereon processor executable instructions configured to cause a processor to perform each of the inventive method steps b) to h).
  • the invention relates to a computing device for predicting a specific respiratory pathogen in a group of farm animals, the computing device comprising means to carry out the method steps b) to h) according to the invention.
  • the invention relates to a kit of parts for carrying out each of the method steps according to the invention consisting essentially of
  • (C) optionally an information booklet providing instruction for the installation and utilization of (A) and (B).
  • FIG. 1 is a process flow diagram illustrating an embodiment of the method according to the invention.
  • FIG. 2 illustrates the resulting output data showing RDI pattern caused by Swine Influenza Virus.
  • FIG. 3 illustrates the resulting output data showing RDI pattern caused by Mycoplasma
  • FIG. 4 illustrates the resulting output data showing RDI pattern caused by Actinobacillus
  • FIG. 5 illustrates the resulting output data showing RDI pattern caused by Porcine Reproductive and Respiratory Syndrome (PRRS) virus.
  • PRRS Porcine Reproductive and Respiratory Syndrome
  • FIG. 6 illustrates an exemplary arrangement of the sound monitoring system in a farm stable.
  • infectious pathogen as used hereinabove or hereinbelow in its oldest and broadest sense is anything that can produce a respiratory disease. It embraces both infectious agents such as viruses, bacteria, prions, fungi, or even other micro-organisms; and non-infectious agents such as chemical gaseous agents including ammonia, hydrogen sulfide, carbon dioxide and methane, organic dust originating from feed, fecal particles or dander, endotoxins including coliforms in fecal dust, and smoke.
  • infectious agents such as viruses, bacteria, prions, fungi, or even other micro-organisms
  • non-infectious agents such as chemical gaseous agents including ammonia, hydrogen sulfide, carbon dioxide and methane, organic dust originating from feed, fecal particles or dander, endotoxins including coliforms in fecal dust, and smoke.
  • predicting pathogens means that the pattern of the RDI values obtained in a specific farm, stable or part of a stable are compared with a library or table of RDI patterns obtained from monitoring farm animals, which had been infected by a specific pathogen. If the actual pattern matches with one of the stored pathogen specific patterns, it can be predicted, that at least one animal in the monitored group is infected with the matching pathogen.
  • predicting pathogens does not include the attribution of the deviation to a particular clinical picture on a specific animal, i.e. the deductive veterinary decision. Nevertheless, it is a helpful tool for the veterinarian which may form part of such decision.
  • pathogen specific RDI pattern means the pattern of the RDI values caused by a specific respiratory pathogen. It includes the form of the curve of the these RDI values with the time, the steepness of increase of the RDI values as well as the area under the curve. All these features are pathogen-specific and are stored in the table of the computing device. Such a table had been established previously with by simultaneously measuring the sounds in farm animals, calculating the RDI values and diagnosing the correlating pathogen causing the respiratory distress sounds.
  • sounds of respiratory distress as used hereinabove or hereinbelow includes all kinds of sounds that farm animals make due to respiratory disorders or diseases including but not limited to coughing, sneezing, harrumphing and wheezing.
  • farm animals as used hereinabove or hereinbelow includes all kinds of animals which are maintained in a farm for production of animal product or for leisure, such as, horses, dogs, donkeys, ostriches and minks, in particular pigs, cattle, horses and poultry.
  • processor means a computing device such as an industrial computer, personal computer (PC), laptop, or tablet, which may be located within the farm, stable, or section of a stable, or is connected via data transfer means with a microphone located within the farm, stable, or section of a stable.
  • PC personal computer
  • connection or “connectable” used hereinabove or hereinbelow with respect to the relationship of the microphone and the computing device is intended to include any direct linkage by a suitable cable or wire, but also any wireless connection such as infrared, Bluetooth or WLAN.
  • computing device means not only a processor in a housing connected to the microphone, but also includes a system comprising a device that first receives the acoustic data from the microphone, then stores such data in a processor readable medium and later transmits it to a processor.
  • processor readable medium includes any medium that can be used to store digital data including but not limited to internal or external hard drives, SSD drives, SDI cards, storage clouds, CDs, DVDs, USB sticks, floppy discs and magnetic tapes.
  • comparing data of the resulting RDI pattern includes the comparison of pathogen specific or library with the actual RDI pattern obtained from a group of the farm animals.
  • the total number of RDIs or the area under the curve, the number of RDI maxima, the time to reach the first and any following maximum, the time of decline from any maximum of the actual RDI pattern obtained from a group of the farm animals will be compared with the corresponding features of the pathogen specific RDI patterns stored in the table.
  • the processor will determine the difference between these features of the actual RDI pattern and the RDI patterns stored in the table and indicate the pathogen, for which this difference forms a minimum.
  • a method wherein (a) the farm animals are selected from the group consisting of cattle, pigs and poultry, in particular growing/ fattening pigs or breeding pigs;
  • the respiratory pathogens of the stored table have been verified by diagnostic one or more methods, preferably by a pen-based oral fluid sampling combined with an enzyme-linked immunosorbent assay (ELISA) or polymerase chain reaction (PCR) and/or blood serum testing.
  • diagnostic one or more methods preferably by a pen-based oral fluid sampling combined with an enzyme-linked immunosorbent assay (ELISA) or polymerase chain reaction (PCR) and/or blood serum testing.
  • ELISA enzyme-linked immunosorbent assay
  • PCR polymerase chain reaction
  • the respiratory pathogen is selected from the group consisting of one or more bacteria, mycoplasmas and viruses, preferably from the group consisting of Acinetobacter,
  • Actinobacillus in particular Actinobacillus Pleuropneumiae (APP), Arcanobacterium, Bordetella, Haemophilus, Klebsiella, Pasteurella, Salmonella, Streptococcus, M. hyorhinis, M. hyopneumoniae, Swine Influenza, Porcine Reproductive and Respiratory Syndrome (PRRS) virus, Respiratory coronavirus, Porcine circovirus type 2 (PCV2), Porcine cytomegalovirus, Aujeszky's Disease, Classical swine fever and African swine fever, in particular APP, M. hyopneumoniae, Swine Influenza, PRRS and PCV2, most preferably Swine Influenza;
  • PRRS Porcine Reproductive and Respiratory Syndrome
  • the respiratory pathogen is selected from the group consisting of non-infectious agents such as chemical gaseous agents including ammonia, hydrogen sulfide, carbon dioxide and methane, organic dust originating from feed, fecal particles or dander, endotoxins including coliforms in fecal dust, and smoke
  • the sound caused by respiratory distress is sneezing and/or coughing
  • the sounds generated in the group of the farm animals are recorded continuously over a period of at least two weeks, preferably 1 to 12 months;
  • step a) the noises produced by 1 to 1000 farm animals are recorded using 1 to 4
  • microphones depending on the size of the monitored farm animals, in preferably 5 to 200 pigs, 10 to 1000 chicken, or 1 to 50 cows.
  • step c) the stored data generated from the sounds produced by a group of healthy farm animals is used to filter off the background noise.
  • the RDI is the number of sounds caused by respiratory distress per single farm animal within 5 to 48, preferably 12 to 36, in particular about 24 hours, in another preferred embodiment during hours of low activity in the farm such as the night time.
  • the stored table of respiratory pathogens comprises 1 to 10, preferably 2 to 6 different respiratory pathogens, in particular APP, M. hyopneumoniae, Swine Influenza,
  • the processor produces a report indicating one or more RDI values that exceeded the threshold RDI value and/or transmits such report to the stockman or veterinarian health professional, who is in charge of the group of farm animals.
  • the hardware used to capture the sounds was a' SOMO+ sound recording device of SoundTalks BV, Belgium.
  • the phantom-powered (i.e., DC electric power is transmitted through the microphone cables to operate the microphones that contain active electronic circuitry) microphones were connected in a balanced way. This permits the use of long microphone cables, with limited susceptibility to noise.
  • the microphones were typically centered with respect to the position of the animals that were monitored (e.g., pigpen).
  • the microphones were fixed at a height of 2 meters to be close enough to animals, yet not too close for the animals to reach them. Recordings were continuous (24/24, 7d/w) in files of 5 minutes duration.
  • the recording parameters were set to 16 signed integer bit resolution, with a sampling rate of 22.05 kHz (standard WAV file format).
  • the embedded sound card was fanless and protected from the harsh environment by a sealed enclosure.
  • the microphone was protected from the environment by a thin and flexible cover, designed to not interfere with the sound acquisition in the frequency range of interest, i.e., from 1 kHz to 5 kHz.
  • the equipment much like similar PLF technologies, was subject to a range of robustness-related issues typical in the farm environment.
  • various diagnostic tests such as (discrete) saliva or serum drawings were carried out. The saliva and serum drawings were tested for
  • APP Actinobacillus Pleuropneumiae
  • SIAV Swine Influenza Virus
  • Hyopneumoniae M. Hyo
  • PRRSV Porcine reproductive and respiratory syndrome virus
  • swine influenza virus (SIAV)
  • the term swine influenza virus refers to a type A or type C influenza virus from the family orthomyxovirus that causes swine influenza. While orthomyxovirus has three groups: type A, type B and type C, only type A and type C influenza viruses infect pigs.
  • the swine influenza virus is a Swine Influenza A virus.
  • Subtypes of swine influenza virus include H1N1, H1N2, H3N2, and H3N1.
  • H9N2 and H5 1 can also be found in pigs.
  • the animals will be infected with a specific pathogen and the sounds caused by the respiratory distress is monitored over a certain time period after the infection and the resulting RDI pattern is used, as the pathogen-specific RDI pattern for said pathogen.
  • the patterns of these pathogen-specific RDI values are stored as a table or library in the computing device.
  • the process flow diagram of FIG. 1 shows how one or more microphones (1) first pickup the sounds that occur in a farm, stable or part of the stable. The sounds are then converted from an analogue to a digital signal by an analogue -to -digital converter (2). After digitalization, different filtering techniques (3) are applied to separate respiratory distress sounds from all other sounds that are captured by the microphone(s).
  • the other sounds include both stationary background sounds like e.g. fan noise or feeding line noise, and also transient sound events that are not related to respiratory distress, such as e.g. knocks or screams.
  • the respiratory distress index (RDI) (5) is then calculated as the number of sounds (4) caused by respiratory distress within a pre-defined period of time, scaled with the number of captured farm animals (6), i.e. those in the vicinity of the microphone(s) (1) as shown in FIG. 3A.
  • the RDI values are stored over a period of time and a series of historical RDI values (8), which are accompanied by diagnostic testing to verify the pathogen causing the respiratory distress sounds, serve as input for the determination of the pathogen-specific RDI values (10).
  • the patterns of these pathogen-specific values (11) are stored in a table of the computing device.
  • the actual calculated RDI pattern (7) is then compared with the stored patterns of these pathogen-specific RDI values (1 1). This comparison (12) serves as the output of the method (13), reporting the resulting pathogen as well as the pattern of the RDI values.
  • FIG. 2 shows an example of the method according to the invention with pigs that were infected with Swine Influenza Virus. The sounds of the animals were monitored between June and October
  • FIG. 2A shows the intensity of respiratory distress sounds as in form of the lighter bars (14, 15) during each day within 24 hours.
  • the ordinate (16) indicates the hours of the day and the X-axis
  • FIGs. 2B to 2D show the intensity of respiratory distress sounds as in form of the lighter bars (14,
  • X-axis (17) shows the dates of the monitoring period.
  • FIG. 2E to FIG. 2H indicate the corresponding RDI (from clipped) values (18) and FIG. 21 to FIG. 2L indicate the corresponding RDI values (19).
  • FIG. 3 shows an example of the method according to the invention with pigs that were infected with Mycoplasma hyopneumoniae indicating the corresponding RDI values (19). The sounds of the animals were monitored between November 11 and December 8, 2015 (17). The arrangement of the sound monitoring system in farm stables was as shown in FIG. 6B.
  • the pre-determined pathogen-specific RDI pattern of Mycoplasma hyopneumoniae is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored Mycoplasma hyopneumoniae RDI pattern and indicates Mycoplasma hyopneumoniae as the pathogen that caused the actual RDI pattern.
  • FIG. 4 shows an example of the method according to the invention with pigs that were infected with Actinobacillus Pleuropneumiae (APP) indicating the corresponding RDI values (19).
  • APP Actinobacillus Pleuropneumiae
  • the sounds of the animals were monitored between January 9 and 20 (17, 18). Initially the trial was carried out with ten pigs. The animals were infected with APP on January 12.
  • the pre-determined pathogen-specific RDI pattern of APP is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored APP RDI pattern and indicates APP as the pathogen that caused the actual RDI pattern.
  • FIG. 5 shows an example of the method according to the invention with pigs that were infected with Porcine Reproductive and Respiratory Syndrome (PRRS) virus indicating the corresponding RDI values (19).
  • PRRS Porcine Reproductive and Respiratory Syndrome
  • the sounds of the animals were monitored between August 7 and September 1 1 (17, 18). Initially the trial was carried out with ten pigs, 4 weeks of age. The animals were infected with PRRS on August 7. The slightly enhanced RDI values between August 8 and 14 (19a) were not caused by PRRS, but by an endemic Mycoplasma hyopneumoniae infection.
  • the pre-determined pathogen-specific RDI pattern of PRRS is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored PRRS RDI pattern and indicates PRRS as the pathogen that caused the actual RDI pattern.
  • FIG. 6 illustrates different exemplary arrangements of the sound monitoring system in farm stables.
  • FIG. 6A shows a schematic cross-section of a pig stable (22), in which the microphone (1) is mounted at the ceiling (23) of the stable in a height of about 2 meters. The sounds made by all animals (6) within a radius of about 7 to 9 meters on the ground (24) are within the reach of the microphone.
  • FIG. 6B shows a top view of six pigpens with a length of about 6 meters and a width of about 5 meters.
  • the total pig population is 225.
  • One microphone records the sounds made by about 75% of the animals.
  • FIG. 6C shows a top view of eight pigpens with a length of about 6 meters and a width of about 5 meters.
  • the total pig population is 320.
  • Two microphones record the sounds made by all the animals.
  • FIG. 6D shows a top view of twenty-four pigpens with a length of about 6 meters and a width of about 5 meters.
  • the total pig population is 1000.
  • Four microphones record the sounds made by about 75% of the animals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Environmental Sciences (AREA)
  • Quality & Reliability (AREA)
  • Biomedical Technology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Pulmonology (AREA)
  • Epidemiology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention relates to a method carried out by a processor for predicting a specific respiratory pathogen in a group of farm animals, which method comprises monitoring the sounds generated by said farm animals.

Description

METHOD FOR PREDICTING A SPECIFIC RESPIRATORY PATHOGEN
CROSS-REFERENCE TO RELATED APPLICATIONS
This application claims the benefit from the priority of European patent application EP 16002421.2 filed on November 15, 2016; the entire content of this application is hereby incorporated by reference.
BACKGROUND OF THE INVENTION
1. TECHNICAL FIELD
The invention relates to a method carried out by a processor for predicting a specific respiratory pathogen in a group of farm animals comprising recording the sounds; converting the analog recording into digital data; filtering off background noises from sounds caused by respiratory distress; comparing the resulting the respiratory distress index (RDI) pattern with a stored table containing data of different RDI patterns generated by several different respiratory pathogens; and reporting the respiratory pathogen, which corresponds to the matching RDI patterns.
Furthermore, the invention relates to a non-transitory processor readable medium having stored thereon processor executable instructions configured to cause a processor to perform the method according to the invention, a computing device to carry out the method according to the invention, and a kit of parts for carrying out the inventive method comprising such a computing device and at least one microphone.
2. BACKGROUND INFORMATION
In recent years, several factors have stressed traditional livestock farming. Firstly, the global meat demand has grown extremely as the world population continues to grow. Furthermore, income per capita is increasing, particularly in the upcoming industries like the BRIC-countries. This enables massive new groups of people to consume meat. Another trend specific to consumers in developed countries is the augmented concern towards ethical and environmentally friendly meat production. Additionally, there is a clear need for a reduction in the use of antibiotics in intensive livestock production (Aarestrup, F. 2012, Nature 486, 465-466; Kimman, T., Smits, M., Kemp, B., Wever, P., and Verheijden, J. 2010. Banning Antibiotics, Reducing Resistance, Preventing and Fighting Infections: White Paper on Research Enabling an Antibiotic-free' Animal Husbandry. Wageningen Academic UR).
Livestock farming may be regarded as a process control technology, in which context the Precision Livestock Farming (PLF) is often used (Berckmans, D. 2006, in Livestock Production and Society, R. Geers, and F. Madec, eds. Wageningen Academic Publishers. 51-54). Different kinds of sensors are employed to facilitate PLF in a practical setup, e.g., cameras (CCTV, infra-red, 3D, thermal...), accelerometers, flow meters, etc.. A particularly interesting type of PLF techniques uses microphones to capture sound. Sound contains a lot of useful information about the animal and its environment (communication, health, welfare). Recently, a number of examples of sound-based PLF -techno logy have emerged in different species. Moura et al. showed how thermal (dis-) comfort can be monitored in broilers based on sound analysis (Moura, D.J. de, Naiis, I. de A., Alves, E.C. de S., Carvalho, T.M.R. de, do Vale, M.M., and Lima, K.A.O. de 2008, Sci. Agric. 65, 438- 443), while Aydin et al. demonstrated the monitoring of broiler feed intake by pecking sounds (Aydin, A., Bahr, C, Viazzi, S., Exadaktylos, V., Buyse, J., and Berckmans, D. 2014. Comput. Electron. Agric. 101, 17-23). Hillman et al. used acoustic monitoring of pigs for the detection of thermal (dis-) comfort (Hillmann, E., Mayer, C, Schon, P.-C, Puppe, B., and Schrader, L. 2004, Appl. Anim. Behav. Sci. 89, 195-206).
Van Hirtum et al. first developed algorithms to discriminate pathological from non-pathological pig coughs (Van Hirtum, A. 2002. The acoustics of coughing. PhD Thesis. KU Leuven. Leuven,
Belgium). Ferrari et al. did a characterisation of pig cough sounds using time and frequency-derived parameters (Ferrari et al., 2008),
The link between automatically measured cough and anomalies in respiratory porcine behaviour has been validated extensively in several field trials (Finger, G., Hemeryck, M., Gomez-Duran, O., and Genzow, M. 2014, in Proceedings of the 23rd IPVS Congress, Cancun, Mexico. 207-208; Genzow, M., Gomez-Duran, O., Hemeryck, M., and Finger, G. 2014a, in Proceedings of the 23rd IPVS Congress, Cancun, Mexico. 212-213; Genzow, M., Gomez-Duran, O., Strutzberg -Minder, K., Finger, G., and Hemeryck, M. 2014b, in Proceedings of the 23rd IPVS Congress, Cancun, Mexico. 205-206; Berckmans, D , Hemeryck, M., Berckmans, D., Vranken, E., van Waterschoot, T., 2015 in Int. Symp. on Animal Environ. & Welfare Oct. 23-26, 2015, Chongqing, China).
The European patent application EP 2783 629 Al discloses a method and/or system for monitoring the sounds of a group of farm animals with a microphone connected with a computing device, in which the computing device records the sounds made by the animals, performs filtering operations to filter off background noises, counting the number of sounds caused by respiratory distress over a certain period of time and alerts an operator, if the registered number of sounds caused by respiratory distress exceeds a given value. The International patent application WO 2008/152433 teaches a method and/or system for combining the respiratory status (e.g. amount and type of cough) with the localization of organisms having the respiratory status in real time. Furthermore, it suggests that the type of cough may be recognized utilizing Auto Regression analysis. However, the hitherto described methods are not capable to predict the pathogen, which causes the respiratory distress of the animals monitored. Accordingly, there is a high demand for a
measurement of sounds caused by respiratory distress in farm animals, which can be used as a diagnostic tool to predict the pathogen causing the distress. The problem underlying the present invention was to provide a method to measure sounds caused by respiratory stress in farm animals, which allows predicting the pathogen causing the respiratory stress.
It has now been found surprisingly that each respiratory pathogen creates a distinctive pattern of the respiratory distress index (RDI) being the number of sounds caused by respiratory distress per single farm animal within a pre-defined period. The problem underlying the present invention has been solved by a method wherein the pattern of the RDI is measured, monitored and stored period of time and compared with a table in which different RDI patterns are stored.
BRIEF SUMMARY OF THE INVENTION
Accordingly, the invention relates to a method for predicting a specific respiratory pathogen in a group of farm animals, comprising the following steps:
a) recording the sounds generated in the group of the farm animals over a certain period of time;
b) converting the analog recording into digital data;
c) performing filtering operations, which filter off background noises from sounds caused by respiratory distress;
d) counting the number of sounds caused by respiratory distress during the recordal time; e) calculating the respiratory distress index (RDI) being the number of sounds caused by respiratory distress within a pre-defined period of time, optionally corrected by the number of farm animals within the reach of each microphone;
f) monitoring and storing the pattern of the RDI over a period of time;
g) comparing data of the resulting RDI pattern with a stored table containing data of different RDI patterns generated by several different respiratory pathogens; and
h) reporting the respiratory pathogen, which corresponds to the matching RDI patterns, wherein the steps b) to h) are carried out by a processor.
The invention further relates to a non-transitory processor readable medium having stored thereon processor executable instructions configured to cause a processor to perform each of the inventive method steps b) to h).
Furthermore, the invention relates to a computing device for predicting a specific respiratory pathogen in a group of farm animals, the computing device comprising means to carry out the method steps b) to h) according to the invention. In addition, the invention relates to a kit of parts for carrying out each of the method steps according to the invention consisting essentially of
(A) an inventive computing device;
(B) at least one microphone connectable with said computing device (A); and
(C) optionally an information booklet providing instruction for the installation and utilization of (A) and (B).
BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings illustrate embodiments of the invention, and, together with specification, including the general description above and the detailed description, which follows, serve to explain the features of the present invention.
FIG. 1 is a process flow diagram illustrating an embodiment of the method according to the invention.
FIG. 2 illustrates the resulting output data showing RDI pattern caused by Swine Influenza Virus. FIG. 3 illustrates the resulting output data showing RDI pattern caused by Mycoplasma
hyopneumoniae.
FIG. 4 illustrates the resulting output data showing RDI pattern caused by Actinobacillus
Pleuropneumiae (APP).
FIG. 5 illustrates the resulting output data showing RDI pattern caused by Porcine Reproductive and Respiratory Syndrome (PRRS) virus.
FIG. 6 illustrates an exemplary arrangement of the sound monitoring system in a farm stable.
DETAILED DESCRIPTION OF THE INVENTION
The term "respiratory pathogen" as used hereinabove or hereinbelow in its oldest and broadest sense is anything that can produce a respiratory disease. It embraces both infectious agents such as viruses, bacteria, prions, fungi, or even other micro-organisms; and non-infectious agents such as chemical gaseous agents including ammonia, hydrogen sulfide, carbon dioxide and methane, organic dust originating from feed, fecal particles or dander, endotoxins including coliforms in fecal dust, and smoke. The term "predicting pathogens" as used hereinabove or hereinbelow means that the pattern of the RDI values obtained in a specific farm, stable or part of a stable are compared with a library or table of RDI patterns obtained from monitoring farm animals, which had been infected by a specific pathogen. If the actual pattern matches with one of the stored pathogen specific patterns, it can be predicted, that at least one animal in the monitored group is infected with the matching pathogen.
The term "predicting pathogens" does not include the attribution of the deviation to a particular clinical picture on a specific animal, i.e. the deductive veterinary decision. Nevertheless, it is a helpful tool for the veterinarian which may form part of such decision.
The term "pathogen specific RDI pattern" as used hereinabove or hereinbelow means the pattern of the RDI values caused by a specific respiratory pathogen. It includes the form of the curve of the these RDI values with the time, the steepness of increase of the RDI values as well as the area under the curve. All these features are pathogen-specific and are stored in the table of the computing device. Such a table had been established previously with by simultaneously measuring the sounds in farm animals, calculating the RDI values and diagnosing the correlating pathogen causing the respiratory distress sounds. The term "sounds of respiratory distress" as used hereinabove or hereinbelow includes all kinds of sounds that farm animals make due to respiratory disorders or diseases including but not limited to coughing, sneezing, harrumphing and wheezing.
The term "farm animals" as used hereinabove or hereinbelow includes all kinds of animals which are maintained in a farm for production of animal product or for leisure, such as, horses, dogs, donkeys, ostriches and minks, in particular pigs, cattle, horses and poultry.
The term "processor" as used hereinabove or hereinbelow means a computing device such as an industrial computer, personal computer (PC), laptop, or tablet, which may be located within the farm, stable, or section of a stable, or is connected via data transfer means with a microphone located within the farm, stable, or section of a stable.
The term "connected" or "connectable" used hereinabove or hereinbelow with respect to the relationship of the microphone and the computing device is intended to include any direct linkage by a suitable cable or wire, but also any wireless connection such as infrared, Bluetooth or WLAN.
The term "computing device" as used hereinabove and hereinbelow means not only a processor in a housing connected to the microphone, but also includes a system comprising a device that first receives the acoustic data from the microphone, then stores such data in a processor readable medium and later transmits it to a processor.
The term " processor readable medium" as used hereinbefore or hereinbelow includes any medium that can be used to store digital data including but not limited to internal or external hard drives, SSD drives, SDI cards, storage clouds, CDs, DVDs, USB sticks, floppy discs and magnetic tapes.
The term "comparing data of the resulting RDI pattern" as used hereinbefore or hereinbelow includes the comparison of pathogen specific or library with the actual RDI pattern obtained from a group of the farm animals. In such a comparison the total number of RDIs or the area under the curve, the number of RDI maxima, the time to reach the first and any following maximum, the time of decline from any maximum of the actual RDI pattern obtained from a group of the farm animals will be compared with the corresponding features of the pathogen specific RDI patterns stored in the table. The processor will determine the difference between these features of the actual RDI pattern and the RDI patterns stored in the table and indicate the pathogen, for which this difference forms a minimum.
The following methods are preferred embodiments of the present invention: A method, wherein (a) the farm animals are selected from the group consisting of cattle, pigs and poultry, in particular growing/ fattening pigs or breeding pigs;
(b) the respiratory pathogens of the stored table have been verified by diagnostic one or more methods, preferably by a pen-based oral fluid sampling combined with an enzyme-linked immunosorbent assay (ELISA) or polymerase chain reaction (PCR) and/or blood serum testing.
(c) the respiratory pathogen is selected from the group consisting of one or more bacteria, mycoplasmas and viruses, preferably from the group consisting of Acinetobacter,
Actinobacillus, in particular Actinobacillus Pleuropneumiae (APP), Arcanobacterium, Bordetella, Haemophilus, Klebsiella, Pasteurella, Salmonella, Streptococcus, M. hyorhinis, M. hyopneumoniae, Swine Influenza, Porcine Reproductive and Respiratory Syndrome (PRRS) virus, Respiratory coronavirus, Porcine circovirus type 2 (PCV2), Porcine cytomegalovirus, Aujeszky's Disease, Classical swine fever and African swine fever, in particular APP, M. hyopneumoniae, Swine Influenza, PRRS and PCV2, most preferably Swine Influenza;
(d) the respiratory pathogen is selected from the group consisting of non-infectious agents such as chemical gaseous agents including ammonia, hydrogen sulfide, carbon dioxide and methane, organic dust originating from feed, fecal particles or dander, endotoxins including coliforms in fecal dust, and smoke
(e) the sound caused by respiratory distress is sneezing and/or coughing;
(f) the sounds generated in the group of the farm animals are recorded continuously over a period of at least two weeks, preferably 1 to 12 months;
(g) in step a) the noises produced by 1 to 1000 farm animals are recorded using 1 to 4
microphones, depending on the size of the monitored farm animals, in preferably 5 to 200 pigs, 10 to 1000 chicken, or 1 to 50 cows.
(h) in step c) the stored data generated from the sounds produced by a group of healthy farm animals is used to filter off the background noise. (i) in step e) the RDI is the number of sounds caused by respiratory distress per single farm animal within 5 to 48, preferably 12 to 36, in particular about 24 hours, in another preferred embodiment during hours of low activity in the farm such as the night time.
(j) in step g) the stored table of respiratory pathogens comprises 1 to 10, preferably 2 to 6 different respiratory pathogens, in particular APP, M. hyopneumoniae, Swine Influenza,
PRRS and PCV2, and their corresponding RDI patterns.
(k) in step h), the processor produces a report indicating one or more RDI values that exceeded the threshold RDI value and/or transmits such report to the stockman or veterinarian health professional, who is in charge of the group of farm animals.
The various embodiments will be described in detail with reference to the accompanying drawings. Where possible the same reference numbers will be used throughout the drawings to refer to the same or like parts. References made to particular examples and implementations are for illustrative purposes, and are not intended to limit the scope of the claims.
The hardware used to capture the sounds was a' SOMO+ sound recording device of SoundTalks BV, Belgium. The phantom-powered (i.e., DC electric power is transmitted through the microphone cables to operate the microphones that contain active electronic circuitry) microphones were connected in a balanced way. This permits the use of long microphone cables, with limited susceptibility to noise. The microphones were typically centered with respect to the position of the animals that were monitored (e.g., pigpen). The microphones were fixed at a height of 2 meters to be close enough to animals, yet not too close for the animals to reach them. Recordings were continuous (24/24, 7d/w) in files of 5 minutes duration. The recording parameters were set to 16 signed integer bit resolution, with a sampling rate of 22.05 kHz (standard WAV file format). The embedded sound card was fanless and protected from the harsh environment by a sealed enclosure. The microphone was protected from the environment by a thin and flexible cover, designed to not interfere with the sound acquisition in the frequency range of interest, i.e., from 1 kHz to 5 kHz. The equipment, much like similar PLF technologies, was subject to a range of robustness-related issues typical in the farm environment. In parallel to the sound monitoring and RDI calculations various diagnostic tests such as (discrete) saliva or serum drawings were carried out. The saliva and serum drawings were tested for
Actinobacillus Pleuropneumiae (APP), Swine Influenza Virus (SIAV), Mycoplasma
Hyopneumoniae (M. Hyo) and Porcine reproductive and respiratory syndrome virus (PRRSV). The diagnostic results showed that the patterns of the RDI values are specific to the pathogen causing the respiratory distress.
The term "swine influenza virus (SIAV)" is known by the person skilled in the art. The term swine influenza virus refers to a type A or type C influenza virus from the family orthomyxovirus that causes swine influenza. While orthomyxovirus has three groups: type A, type B and type C, only type A and type C influenza viruses infect pigs. Preferably, the swine influenza virus is a Swine Influenza A virus. Subtypes of swine influenza virus include H1N1, H1N2, H3N2, and H3N1. H9N2 and H5 1 can also be found in pigs. Alternatively, the animals will be infected with a specific pathogen and the sounds caused by the respiratory distress is monitored over a certain time period after the infection and the resulting RDI pattern is used, as the pathogen-specific RDI pattern for said pathogen.
The patterns of these pathogen-specific RDI values are stored as a table or library in the computing device.
The process flow diagram of FIG. 1 shows how one or more microphones (1) first pickup the sounds that occur in a farm, stable or part of the stable. The sounds are then converted from an analogue to a digital signal by an analogue -to -digital converter (2). After digitalization, different filtering techniques (3) are applied to separate respiratory distress sounds from all other sounds that are captured by the microphone(s). The other sounds include both stationary background sounds like e.g. fan noise or feeding line noise, and also transient sound events that are not related to respiratory distress, such as e.g. knocks or screams. The respiratory distress index (RDI) (5) is then calculated as the number of sounds (4) caused by respiratory distress within a pre-defined period of time, scaled with the number of captured farm animals (6), i.e. those in the vicinity of the microphone(s) (1) as shown in FIG. 3A. The RDI values are stored over a period of time and a series of historical RDI values (8), which are accompanied by diagnostic testing to verify the pathogen causing the respiratory distress sounds, serve as input for the determination of the pathogen-specific RDI values (10). The patterns of these pathogen-specific values (11) are stored in a table of the computing device. The actual calculated RDI pattern (7) is then compared with the stored patterns of these pathogen-specific RDI values (1 1). This comparison (12) serves as the output of the method (13), reporting the resulting pathogen as well as the pattern of the RDI values.
FIG. 2 shows an example of the method according to the invention with pigs that were infected with Swine Influenza Virus. The sounds of the animals were monitored between June and October
2013. The arrangement of the sound monitoring system in farm stables was as shown in FIG. 4B.
FIG. 2A shows the intensity of respiratory distress sounds as in form of the lighter bars (14, 15) during each day within 24 hours. The ordinate (16) indicates the hours of the day and the X-axis
(17) shows the dates of the monitoring.
FIGs. 2B to 2D show the intensity of respiratory distress sounds as in form of the lighter bars (14,
15) during different times of each day, i.e. from 0 to 5 o'clock (FIG 2B), from 6 to 13 o'clock (FIG
2C) and from 14 to 21 o'clock (FIG 2D). The ordinate (16) indicates the hours of the day and the
X-axis (17) shows the dates of the monitoring period.
FIG. 2E to FIG. 2H indicate the corresponding RDI (from clipped) values (18) and FIG. 21 to FIG. 2L indicate the corresponding RDI values (19).
In this example, it is clear that there was a steep increase and decrease of RDI values between July 3 and 10, 2013 (20) and a second steep increase between September 3 and 14, 2013 (21). The highest RDI value is reached already after less than about 5 days. Such narrow, steep peaks are typical for swine influenza. The same is true for the comparably short duration and the small area under the curve.
The pre-determined pathogen-specific RDI pattern of SIAV is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored SIAV RDI pattern and indicates SIAV as the pathogen that caused the actual RDI pattern. FIG. 3 shows an example of the method according to the invention with pigs that were infected with Mycoplasma hyopneumoniae indicating the corresponding RDI values (19). The sounds of the animals were monitored between November 11 and December 8, 2015 (17). The arrangement of the sound monitoring system in farm stables was as shown in FIG. 6B.
In this example, it is clear that there was a very slow increase between November 18 and December 7 (20). The highest RDI value is reached only after about 19 days. Such extremely broad peaks are typical for Mycoplasma hyopneumoniae. The same is true for the very long duration and the large area under the curve.
The pre-determined pathogen-specific RDI pattern of Mycoplasma hyopneumoniae is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored Mycoplasma hyopneumoniae RDI pattern and indicates Mycoplasma hyopneumoniae as the pathogen that caused the actual RDI pattern.
FIG. 4 shows an example of the method according to the invention with pigs that were infected with Actinobacillus Pleuropneumiae (APP) indicating the corresponding RDI values (19). The sounds of the animals were monitored between January 9 and 20 (17, 18). Initially the trial was carried out with ten pigs. The animals were infected with APP on January 12.
In this example, it is clear that there was a very steep increase between January 12 and 15 (20). The highest RDI value is already reached on January 17 (21). Such steep curves with two strong peaks within 2-3 consecutive days are typical for APP.
The pre-determined pathogen-specific RDI pattern of APP is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored APP RDI pattern and indicates APP as the pathogen that caused the actual RDI pattern.
FIG. 5 shows an example of the method according to the invention with pigs that were infected with Porcine Reproductive and Respiratory Syndrome (PRRS) virus indicating the corresponding RDI values (19). The sounds of the animals were monitored between August 7 and September 1 1 (17, 18). Initially the trial was carried out with ten pigs, 4 weeks of age. The animals were infected with PRRS on August 7. The slightly enhanced RDI values between August 8 and 14 (19a) were not caused by PRRS, but by an endemic Mycoplasma hyopneumoniae infection.
In this example, it is clear that almost no respiratory symptoms from the PRRS infection could be detected between August 15 and September 2, but a steep increase of the RDI values began on September 3 (20). The highest RDI values were reached between September 4 and 8 (21). Such steep curves with two to three strong peaks within 2-3 consecutive days after a long during time without respiratory symptoms are typical for PRRS .
Upon deletion of the RDI values caused by the endemic Mycoplasma hyopneumoniae infection (19a), the pre-determined pathogen-specific RDI pattern of PRRS is stored in the computing device and the actually monitored RDI patterns are compared therewith by said computing device, which indicates if the actually monitored RDI pattern matches with the stored PRRS RDI pattern and indicates PRRS as the pathogen that caused the actual RDI pattern.
FIG. 6 illustrates different exemplary arrangements of the sound monitoring system in farm stables. FIG. 6A shows a schematic cross-section of a pig stable (22), in which the microphone (1) is mounted at the ceiling (23) of the stable in a height of about 2 meters. The sounds made by all animals (6) within a radius of about 7 to 9 meters on the ground (24) are within the reach of the microphone.
FIG. 6B shows a top view of six pigpens with a length of about 6 meters and a width of about 5 meters. The total pig population is 225. One microphone records the sounds made by about 75% of the animals.
FIG. 6C shows a top view of eight pigpens with a length of about 6 meters and a width of about 5 meters. The total pig population is 320. Two microphones record the sounds made by all the animals.
FIG. 6D shows a top view of twenty-four pigpens with a length of about 6 meters and a width of about 5 meters. The total pig population is 1000. Four microphones record the sounds made by about 75% of the animals.
The preceding description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications of these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but to be accorded the widest scope consistent with the following claims and the principles and features disclosed herein.

Claims

Patent Claims
1. A method for predicting a specific respiratory pathogen in a group of farm animals, comprising the following steps:
a) recording the sounds generated in the group of the farm animals over a certain period of time;
b) converting the analog recording into digital data;
c) performing a filtering operation, which filters off background noises from sounds caused by respiratory distress;
d) counting the number of sounds caused by respiratory distress during the recording time; e) calculating the respiratory distress index (RDI) being the number of sounds caused by respiratory distress within a pre-defined period of time, optionally corrected for the number of farm animal within the reach of each microphone;
f) monitoring and storing the pattern of the RDI over a period of time;
g) comparing data of the resulting RDI pattern with a stored table containing data of different RDI patterns generated by several different respiratory pathogens; and
h) reporting the respiratory pathogen, which corresponds to the matching RDI patterns, wherein the steps c) to h) are carried out by a processor.
2. The method of claim 1, wherein the farm animals are selected from the group consisting of cattle, pigs, horses and poultry.
3. The method of claim 1 or 2, wherein the respiratory pathogens of the stored table have been verified by diagnostic one or more methods, preferably by a pen-based oral fluid sampling combined with an enzyme-linked immunosorbent assay (ELIS A) or polymerase chain reaction (PCR) and/or blood serum testing.
4. The method according to any one of claims 1 to 3, wherein the respiratory pathogen is an infectious agent selected from the group consisting of one or more bacteria, mycoplasmas and viruses or a non-infectious agent selected from the group consisting of chemical gaseous agents, organic dust, endotoxins and smoke.
5. The method according to any one of claims 1 to 4, wherein the infectious respiratory pathogen is selected from the group consisting of Acinetobacter, Actinobacillus, in particular Actinobacillus Pleuropneumiae (APP), Arcanobacterium, Bordetella, Haemophilus, Klebsiella, Pasteurella, Salmonella, Streptococcus, M. hyorhinis, M. hyopneumoniae, Swine Influenza virus (SIAV), Porcine Reproductive and Respiratory Syndrome (PRRS) virus, Respiratory
coronavirus,Porcine circovirus type 2 (PCV2), Porcine cytomegalovirus, Aujeszky's Disease, Classical swine fever and African swine fever.
6. The method according to claim 5, wherein the infectious respiratory pathogen is selected from the group consisting of APP, M. hyopneumoniae, Swine Influenza, PRRS and PCV2.
7. The method according to any one of claims 1 to 4, wherein the non-infectious pathogen is selected from the group consisting of ammonia, hydrogen sulfide, carbon dioxide and methane, dust originating from feed, fecal particles or dander, coliforms in fecal dust.
8. The method according to any one of claims 1 to 7, wherein in step a) the sounds produced by 1 to 1000 farm animals is recorded using 1 to 4 microphones.
9. The method according to any one of claims 1 to 8, wherein in step e) the RDI is the number of sounds caused by respiratory distress per single farm animal within 24 hours.
10. The method according to any one of claims 1 to 9, wherein in step c) the stored data generated from the sounds produced by a group of healthy farm animals is used to filter off the background noise.
1 1. The method according to any one of claims 1 to 10, wherein in step g) the stored table of respiratory pathogens comprises 1 to 10 respiratory pathogens and their corresponding RDI patterns.
12. The method according to any one of claims 1 to 1 1, wherein in step a) the number of sounds caused by respiratory distress is recorded during hours of reduced activity on the farm, preferably overnight.
13. The method according to any one of claims 1 to 12, wherein in step h), the processor produces a report, preferably on the screen of a computing device or in printed form, indicating the predicted respiratory pathogen and optionally the underlying RDI pattern and/or transmits the report to user, preferably the stockman or the veterinarian health professional, who is in charge of the group of farm animals.
14. A non-transitory processor readable medium having stored thereon processor executable instructions configured to cause a processor to perform each of the method steps c) to h) of any of claims 1 to 13.
15. A computing device for predicting a specific respiratory pathogen in a group of farm animals, the computing device comprising means to carry out the method steps b) to h) of any of claims 1 to 13.
16. A kit of parts for carrying out each of the method steps of any of claims 1 to 13 consisting essentially of
(A) a computing device as claimed in claim 13;
(B) at least one microphone connectable with said computing device (A); and optionally an information booklet providing instruction for the installation and utilization of (A) and (B).
EP17844655.5A 2016-11-15 2017-11-12 Method for predicting a specific respiratory pathogen Active EP3541288B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP16002421 2016-11-15
PCT/EP2017/078972 WO2018091382A1 (en) 2016-11-15 2017-11-12 Method for predicting a specific respiratory pathogen

Publications (2)

Publication Number Publication Date
EP3541288A1 true EP3541288A1 (en) 2019-09-25
EP3541288B1 EP3541288B1 (en) 2023-07-19

Family

ID=57482115

Family Applications (1)

Application Number Title Priority Date Filing Date
EP17844655.5A Active EP3541288B1 (en) 2016-11-15 2017-11-12 Method for predicting a specific respiratory pathogen

Country Status (8)

Country Link
US (1) US10849314B2 (en)
EP (1) EP3541288B1 (en)
CN (1) CN110520053B (en)
DK (1) DK3541288T3 (en)
ES (1) ES2952524T3 (en)
HU (1) HUE063834T2 (en)
PL (1) PL3541288T3 (en)
WO (1) WO2018091382A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3185752B1 (en) 2014-08-28 2020-12-30 Norton (Waterford) Limited Compliance monitoring module for an inhaler
WO2018091383A1 (en) 2016-11-15 2018-05-24 Soundtalks Nv A method for customized monitoring of sounds caused by respiratory distress
CA3138446A1 (en) 2019-04-30 2020-11-05 Norton (Waterford) Limited Inhaler system
KR102571221B1 (en) * 2021-06-02 2023-08-29 주식회사 에스비솔루션 Method and system for managing animal data

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5197490A (en) * 1990-04-19 1993-03-30 Cta Bio Services, Inc. Information processing system for counting coughs or evaluating other activities of a patient
CN100376202C (en) * 1999-06-02 2008-03-26 伊塔马医疗有限公司 Diagnosis of physical condition by monitoring peripheral arterial tone
US6228037B1 (en) * 1999-07-21 2001-05-08 Board Of Trustees Operating Michigan State University Method and apparatus for the recording and analysis of respiratory sounds in exercising horse
IL137381A (en) * 2000-07-19 2005-06-19 Avshalom Bar Shalom Method and system for monitoring ruminant animals, particularly dairy cattle
KR100387201B1 (en) * 2000-11-16 2003-06-12 이병훈 Diaortic apparatus
US20040133079A1 (en) * 2003-01-02 2004-07-08 Mazar Scott Thomas System and method for predicting patient health within a patient management system
US7207948B2 (en) * 2004-06-24 2007-04-24 Vivometrics, Inc. Systems and methods for monitoring cough
US8241223B2 (en) * 2005-04-29 2012-08-14 Isonea Limited Cough detector
US20080275349A1 (en) * 2007-05-02 2008-11-06 Earlysense Ltd. Monitoring, predicting and treating clinical episodes
GB0711524D0 (en) 2007-06-15 2007-07-25 Univ Leuven Kath Online recognition and localisation of sick pig cough sounds
US9043989B2 (en) * 2008-06-04 2015-06-02 Camfil Usa, Inc. Method and apparatus for providing clean air to animal enclosures
US10064580B2 (en) * 2008-11-07 2018-09-04 Intervet Inc. System and method for determining antibiotic effectiveness in respiratory diseased animals using auscultation analysis
US9526429B2 (en) * 2009-02-06 2016-12-27 Resmed Sensor Technologies Limited Apparatus, system and method for chronic disease monitoring
JP5626623B2 (en) * 2010-04-09 2014-11-19 株式会社ハッピーリス Remote diagnostic system
NL1037947C2 (en) * 2010-05-07 2011-11-08 Lely Patent Nv METHOD AND APPARATUS FOR DETERMINING GREENHOUSE GAS EXHAUSTED BY A RETURN, IN PARTICULAR METHANE.
GB201011816D0 (en) * 2010-07-14 2010-09-01 Imp Innovations Feature characterization for breathing monitor
US8777874B2 (en) * 2011-05-24 2014-07-15 Medtronic, Inc. Acoustic based cough detection
EP2830496B1 (en) * 2012-03-29 2023-04-26 The University of Queensland A method and apparatus for processing sound recordings of a patient
US8915215B1 (en) * 2012-06-21 2014-12-23 Scott A. Helgeson Method and apparatus for monitoring poultry in barns
BR112015018929B8 (en) * 2013-02-06 2023-01-31 Geissler Companies Llc ELECTRONIC HEALTH SYSTEM TO DETERMINE THE EFFECTIVENESS OF A DRUG ADMINISTERED USING AUSCULTATION ANALYSIS
FR3003726B1 (en) 2013-03-29 2016-03-04 Nutral Sas SYSTEM FOR THE MANAGEMENT OF THE SANITARY AND RESPIRATORY CONDITION OF BOVINE
CN104736066B (en) * 2013-07-26 2018-07-10 松下电器产业株式会社 Bioacoustic sound testing device and bioacoustic sound testing method
KR101607934B1 (en) * 2014-05-14 2016-03-31 숭실대학교산학협력단 The method for monitoring communicable disease and system using the method, recording medium for performing the method

Also Published As

Publication number Publication date
US10849314B2 (en) 2020-12-01
CN110520053B (en) 2022-08-23
WO2018091382A1 (en) 2018-05-24
CN110520053A (en) 2019-11-29
US20200022337A1 (en) 2020-01-23
PL3541288T3 (en) 2024-01-03
DK3541288T3 (en) 2023-09-11
ES2952524T3 (en) 2023-11-02
EP3541288B1 (en) 2023-07-19
HUE063834T2 (en) 2024-02-28

Similar Documents

Publication Publication Date Title
EP3541288B1 (en) Method for predicting a specific respiratory pathogen
Berckmans et al. Animal sound… talks! Real-time sound analysis for health monitoring in livestock
Trevisan et al. Macroepidemiological aspects of porcine reproductive and respiratory syndrome virus detection by major United States veterinary diagnostic laboratories over time, age group, and specimen
Spangler et al. Leptospiral shedding and seropositivity in shelter dogs in the Cumberland Gap Region of Southeastern Appalachia
Navon et al. Automatic recognition of jaw movements in free-ranging cattle, goats and sheep, using acoustic monitoring
WO2003087765A3 (en) System for tracing animal products
Jordana et al. Evidence of correlated evolution of hypsodonty and exceptional longevity in endemic insular mammals
WO2016073745A3 (en) Automated airborne particulate matter collection, imaging, identification, and analysis
CN102378981A (en) Systems and methods for monitoring the health of anonymous animals in a livestock herd
CN108037717B (en) Intelligent pig farm monitoring system
CN102378980A (en) Vitality meter for monitoring the health of anonymous animals in a livestock herd
Melfsen et al. Describing behavior sequences of fattening pigs using process mining on video data and automated pig behavior recognition
Jenkins et al. Direction of association between bite wounds and Mycobacterium bovis infection in badgers: implications for transmission
Reza et al. A review of sound-based pig monitoring for enhanced precision production
Hoffmann et al. A new approach to recording rumination behavior in dairy cows
Mito et al. Frequency analysis of the sneeze caused by swine influenza virus strains: automatic sneeze around-the-clock detection using a support vector machine
Norton et al. Challenges and opportunities for precision livestock farming applications in the rabbit production sector
Ramos Niño et al. Systematic review of acoustic monitoring in livestock farming: Vocalization patterns and sound source analysis
Ginovart-Panisello et al. Acoustic detection of vaccine reactions in hens for assessing anti-inflammatory product efficacy
EP3541173B1 (en) A method for customized monitoring of sounds caused by respiratory distress
Yan et al. Spatial distribution of airborne bacterial communities in caged poultry houses
Fontana et al. Frequency analysis of vocalisations in relation to the growth in broiler chicken
Hyder et al. Use of spatiotemporal analysis of laboratory submission data to identify potential outbreaks of new or emerging diseases in cattle in Great Britain
Kim et al. Monitoring Multiple Behaviors in Beef Calves Raised in Cow–Calf Contact Systems Using a Machine Learning Approach
Muñoz et al. Aerial Vocalizations by Wild and Rehabilitating Mediterranean Monk Seals (Monachus monachus) in Greece.

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20190617

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20230220

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

P01 Opt-out of the competence of the unified patent court (upc) registered

Effective date: 20230508

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: NL

Ref legal event code: FP

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602017071588

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: DK

Ref legal event code: T3

Effective date: 20230904

REG Reference to a national code

Ref country code: ES

Ref legal event code: FG2A

Ref document number: 2952524

Country of ref document: ES

Kind code of ref document: T3

Effective date: 20231102

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG9D

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1588656

Country of ref document: AT

Kind code of ref document: T

Effective date: 20230719

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231020

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231119

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231120

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231019

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231119

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231020

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

REG Reference to a national code

Ref country code: HU

Ref legal event code: AG4A

Ref document number: E063834

Country of ref document: HU

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602017071588

Country of ref document: DE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed

Effective date: 20240422

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231112

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231112

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

REG Reference to a national code

Ref country code: BE

Ref legal event code: MM

Effective date: 20231130

REG Reference to a national code

Ref country code: IE

Ref legal event code: MM4A

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231112

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231130

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231112

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20231130

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO

Effective date: 20171112

REG Reference to a national code

Ref country code: CH

Ref legal event code: U11

Free format text: ST27 STATUS EVENT CODE: U-0-0-U10-U11 (AS PROVIDED BY THE NATIONAL OFFICE)

Effective date: 20251201

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20230719

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: HU

Payment date: 20251121

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: NL

Payment date: 20251119

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20251119

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20251121

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: IT

Payment date: 20251125

Year of fee payment: 9

Ref country code: DK

Payment date: 20251125

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20251126

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: CH

Payment date: 20251201

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: PL

Payment date: 20251031

Year of fee payment: 9

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: ES

Payment date: 20251229

Year of fee payment: 9